© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128277
    Prev
    Next
    INDEX
    Explanations

    shipping and related costs

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is detecting mentions of shipping costs and related pricing terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gratuita
    -1.43
     colombiano
    -1.37
     corporativa
    -1.35
     gratuito
    -1.32
     vendido
    -1.28
     
    -1.27
     instalado
    -1.27
     favorito
    -1.23
     about
    -1.23
     dolar
    -1.23
    POSITIVE LOGITS
     outspoken
    1.48
    isateurs
    1.47
     You
    1.45
     aid
    1.36
     albeit
    1.33
    ্ষ
    1.30
    你别
    1.28
    weichen
    1.27
    albeit
    1.27
     kleinen
    1.25
    Activations Density 0.027%

    No Known Activations